Looks kinda down there by modern standards,
but typical for low/middle end SCSI.
No SCSI here, but they tell me (by the dozens)
that SCSI is way faster than IDE, so you should probably
be looking for numbers at least as good as my IDE stuff.
This first set of numbers is for a single IDE drive on a P2-400/256MB:
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
512 14622 80.3 16669 16.2 6830 16.0 13983 63.1 17258 16.2 178.1 1.5
The next set is for a pair of slightly slower IDE drives in RAID0:
-------Sequential Output-------- ---Sequential Input-- --Random--
-Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --Seeks---
MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU /sec %CPU
512 17155 94.5 24116 24.2 9653 24.5 16516 70.3 21792 25.3 209.5 1.9
Don't be mislead by the %CPU numbers like many folks are.
They look "high" here simply because the I/O is so fast
that the CPU is seldom idle waiting for something new to do.
-- mlord@pobox.com- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/